Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Long-Term Agentic Memory with LangGraph

  • up to 1 hour
  • Intermediate

Learn to build an agent with long-term memory in this course, created in partnership with LangChain and taught by its Co-Founder and CEO, Harrison Chase. By the end of this course, you will have the foundational mental framework to build an agent with long-term memory using LangGraph.

  • Semantic memory
  • Episodic memory
  • Procedural memory
  • AI agent development
  • Memory integration

Overview

In this course, you will learn how to build an agent with long-term memory by creating a personal email agent that can respond, ignore, and notify the user using writing, scheduling, and memory tools. You’ll develop your agent’s memory by adding facts to its memory store, providing examples to learn the user’s preferences, and optimizing system prompts to evolve instructions based on previous responses. This course will equip you with the skills to integrate semantic, episodic, and procedural memory into AI agents, enhancing their functionality and user interaction.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

AI Enthusiasts

Individuals interested in learning about agentic workflows and long-term memory in AI applications.

Developers

Software developers looking to enhance their skills in building AI agents with memory capabilities.

Data Scientists

Data scientists aiming to integrate long-term memory into AI models for improved performance.

This course offers a unique opportunity to learn how to build AI agents with long-term memory, a crucial aspect for personal assistance and productivity tasks. It covers key concepts like semantic, episodic, and procedural memory, making it ideal for developers and AI enthusiasts looking to enhance their skills. By the end of the course, you'll be equipped to create more effective and responsive AI agents.

Pre-Requisites

1 / 3

  • Familiarity with Python

  • Basic understanding of LLM prompting

  • Basic knowledge of LLM application development

What will you learn?

Introduction
An overview of the course and its objectives, including a brief introduction to agent memory.
Introduction to Agent Memory
Detailed explanation of how memory works in agents, covering semantic, episodic, and procedural memory.
Baseline Email Assistant
Building a basic email assistant with code examples to understand the foundational concepts.
Email Assistant with Semantic Memory
Enhancing the email assistant by integrating semantic memory to store and retrieve user facts.
Email Assistant with Semantic + Episodic Memory
Further development of the email assistant by adding episodic memory for learning user preferences.
Email Assistant with Semantic + Episodic + Procedural Memory
Completing the email assistant by incorporating procedural memory to optimize system prompts.
Conclusion
Summarizing the course content and reinforcing the key learning outcomes.
Quiz
A short quiz to test the knowledge gained throughout the course.
Appendix - Tips and Helps
Additional resources and tips to assist learners in applying the course content.

Upcoming cohorts

  • Dates

    start now

Free